arXiv subjects

Zhi Li

Publications and source records attributed to Zhi Li.

At least 91 records · Page 5Linked to original sources

arXiv2025

MICCAI STSR 2025 Challenge: Semi-Supervised Teeth and Pulp Segmentation and CBCT-IOS Registration

Cone-Beam Computed Tomography (CBCT) and Intraoral Scanning (IOS) are essential for digital dentistry, but annotated data scarcity limits automated solutions for pulp canal segmentation and cross-modal registration. To benchmark semi-supervised learning (SSL) in this domain, we organized the STSR 2025 Challenge at MICCAI 2025, featuring two tasks: (1) semi-supervised segmentation of teeth and pulp canals in CBCT, and (2) semi-supervised rigid registration of CBCT and IOS. We provided 60 labeled and 640 unlabeled IOS samples, plus 30 labeled and 250 unlabeled CBCT scans with varying resolutions and fields of view. The challenge attracted strong community participation, with top teams submitting open-source deep learning-based SSL solutions. For segmentation, leading methods used nnU-Net and Mamba-like State Space Models with pseudo-labeling and consistency regularization, achieving a Dice score of 0.967 and Instance Affinity of 0.738 on the hidden test set. For registration, effective approaches combined PointNetLK with differentiable SVD and geometric augmentation to handle modality gaps; hybrid neural-classical refinement enabled accurate alignment despite limited labels. All data and code are publicly available at https://github.com/ricoleehduu/STS-Challenge-2025 to ensure reproducibility.

cs.CV↗

arXiv2025

Demystifying Feature Engineering in Malware Analysis of API Call Sequences

Machine learning (ML) has been widely used to analyze API call sequences in malware analysis, which typically requires the expertise of domain specialists to extract relevant features from raw data. The extracted features play a critical role in malware analysis. Traditional feature extraction is based on human domain knowledge, while there is a trend of using natural language processing (NLP) for automatic feature extraction. This raises a question: how do we effectively select features for malware analysis based on API call sequences? To answer it, this paper presents a comprehensive study of investigating the impact of feature engineering upon malware classification.We first conducted a comparative performance evaluation under three models, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Transformer, with respect to knowledge-based and NLP-based feature engineering methods. We observed that models with knowledge-based feature engineering inputs generally outperform those using NLP-based across all metrics, especially under smaller sample sizes. Then we analyzed a complete set of data features from API call sequences, our analysis reveals that models often focus on features such as handles and virtual addresses, which vary across executions and are difficult for human analysts to interpret.

cs.CR↗

arXiv2025

MICCAI STS 2024 Challenge: Semi-Supervised Instance-Level Tooth Segmentation in Panoramic X-ray and CBCT Images

Orthopantomogram (OPGs) and Cone-Beam Computed Tomography (CBCT) are vital for dentistry, but creating large datasets for automated tooth segmentation is hindered by the labor-intensive process of manual instance-level annotation. This research aimed to benchmark and advance semi-supervised learning (SSL) as a solution for this data scarcity problem. We organized the 2nd Semi-supervised Teeth Segmentation (STS 2024) Challenge at MICCAI 2024. We provided a large-scale dataset comprising over 90,000 2D images and 3D axial slices, which includes 2,380 OPG images and 330 CBCT scans, all featuring detailed instance-level FDI annotations on part of the data. The challenge attracted 114 (OPG) and 106 (CBCT) registered teams. To ensure algorithmic excellence and full transparency, we rigorously evaluated the valid, open-source submissions from the top 10 (OPG) and top 5 (CBCT) teams, respectively. All successful submissions were deep learning-based SSL methods. The winning semi-supervised models demonstrated impressive performance gains over a fully-supervised nnU-Net baseline trained only on the labeled data. For the 2D OPG track, the top method improved the Instance Affinity (IA) score by over 44 percentage points. For the 3D CBCT track, the winning approach boosted the Instance Dice score by 61 percentage points. This challenge confirms the substantial benefit of SSL for complex, instance-level medical image segmentation tasks where labeled data is scarce. The most effective approaches consistently leveraged hybrid semi-supervised frameworks that combined knowledge from foundational models like SAM with multi-stage, coarse-to-fine refinement pipelines. Both the challenge dataset and the participants' submitted code have been made publicly available on GitHub (https://github.com/ricoleehduu/STS-Challenge-2024), ensuring transparency and reproducibility.

eess.IV↗

arXiv2025

Graph Neural Networks Based Analog Circuit Link Prediction

Circuit link prediction, which identifies missing component connections from incomplete netlists, is crucial in analog circuit design automation. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats restricts model flexibility. We propose Graph Neural Networks Based Analog Circuit Link Prediction (GNN-ACLP), a graph neural networks (GNNs) based method featuring three innovations to tackle these challenges. First, we introduce the SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool that leverages retrieval-augmented generation (RAG) with a large language model (LLM) to enhance the compatibility of netlist formats. Finally, we build a comprehensive dataset, SpiceNetlist, comprising 775 annotated circuits of 7 different types across 10 component classes. Experiments demonstrate accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI compared to the baseline in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, demonstrating robust feature transfer capabilities. However, its linear computational complexity makes processing large-scale netlists challenging and requires future addressing.

cs.AR↗

arXiv2025

Observational properties of a Schwarzschild black hole surrounded by a Dehnen-type dark matter halo

This study investigates the accretion process and observational signatures of thin accretion disks around a Schwarzschild black hole (BH) embedded in a Dehnen-type dark matter (DM) halo. We examine the influence of the density ρ_{s} and radius r_{s} of the DM halo on key disk properties, including the energy flux, temperature distribution, and emission spectrum. Our results show that all three of these quantities decrease with increasing ρ_{s} or r_{s}. Furthermore, by generating and analyzing both direct and secondary images of the accretion disk, we explore how the observational inclination angle and the DM halo parameters ρ_{s} and rs affect image profiles. Finally, the observed flux distributions are presented for different inclination angles. Our findings indicate that the accretion disk becomes colder and dimmer as the DM halo parameters increase, highlighting the significant role of DM in shaping BH observables.

astro-ph.HE↗

arXiv2025

Anderson-skin dualism: A boundary-dependent effect in non-Hermitian disordered coupled systems

We report a novel localization phenomenon that emerges in non-Hermitian and quasiperiodic coupled systems, which we dub ``Anderson-Skin (AS) dualism". The emergence of AS dualism is due to the fact that non-Hermitian topological systems provide non-trivial topological transport channels for disordered systems, causing the originally localized Anderson modes to transform into skin modes, i.e., the localized states within the point gap regions have dual characteristics of localization under periodic boundary condition (PBC) and skin effects under open boundary conditions (OBC). As an example, we analytically prove the 1D AS dualism through the transfer matrix method. Moreover, by discussing many-body interacting systems, we confirm that AS dualism is universal.

cond-mat.dis-nn↗

arXiv2025

A Survey on Deep Text Hashing: Efficient Semantic Text Retrieval with Binary Representation

With the rapid growth of textual content on the Internet, efficient large-scale semantic text retrieval has garnered increasing attention from both academia and industry. Text hashing, which projects original texts into compact binary hash codes, is a crucial method for this task. By using binary codes, the semantic similarity computation for text pairs is significantly accelerated via fast Hamming distance calculations, and storage costs are greatly reduced. With the advancement of deep learning, deep text hashing has demonstrated significant advantages over traditional, data-independent hashing techniques. By leveraging deep neural networks, these methods can learn compact and semantically rich binary representations directly from data, overcoming the performance limitations of earlier approaches. This survey investigates current deep text hashing methods by categorizing them based on their core components: semantic extraction, hash code quality preservation, and other key technologies. We then present a detailed evaluation schema with results on several popular datasets, followed by a discussion of practical applications and open-source tools for implementation. Finally, we conclude by discussing key challenges and future research directions, including the integration of deep text hashing with large language models to further advance the field. The project for this survey can be accessed at https://github.com/hly1998/DeepTextHashing.

cs.IR↗

arXiv2025

WeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging

Cross-Domain Sequential Recommendation (CDSR) seeks to improve user preference modeling by transferring knowledge from multiple domains. Despite the progress made in CDSR, most existing methods rely on overlapping users or items to establish cross-domain correlations-a requirement that rarely holds in real-world settings. The advent of large language models (LLM) and model-merging techniques appears to overcome this limitation by unifying multi-domain data without explicit overlaps. Yet, our empirical study shows that naively training an LLM on combined domains-or simply merging several domain-specific LLMs-often degrades performance relative to a model trained solely on the target domain. To address these challenges, we first experimentally investigate the cause of suboptimal performance in LLM-based cross-domain recommendation and model merging. Building on these insights, we introduce WeaveRec, which cross-trains multiple LoRA modules with source and target domain data in a weaving fashion, and fuses them via model merging. WeaveRec can be extended to multi-source domain scenarios and notably does not introduce additional inference-time cost in terms of latency or memory. Furthermore, we provide a theoretical guarantee that WeaveRec can reduce the upper bound of the expected error in the target domain. Extensive experiments on single-source, multi-source, and cross-platform cross-domain recommendation scenarios validate that WeaveRec effectively mitigates performance degradation and consistently outperforms baseline approaches in real-world recommendation tasks.

cs.IR↗

arXiv2025

GaN-based Resonant Cavity LEDs Fabricated by Photo-Electrochemical Etching and Micro-Transfer Printing

Resonant cavity LEDs (RCLEDs) exhibit excellent temporal and spatial coherence with narrow spectral linewidth and small divergence angle, which is of great importance for micro-displays. In this paper, we demonstrate a novel method to create GaN-based RCLEDs by using photo-electrochemical etching and micro-transfer printing (MTP) technology. Through systematic optimizing of the etching conditions, highly selective etching of an InGaN multiple quantum well sacrificial layer is achieved with parasitic etching of adjacent layers being completely suppressed. The roughness of the underside of the exfoliated GaN film is only 3.3 nm. Raman spectroscopy shows that the residual stress in the released material is reduced from 0.74 GPa for the as-grown sample to -0.15 GPa. Using the MTP method, GaN coupons with a deposited upper dielectric mirror were transferred onto target substrates covered with either an Al mirror or dielectric distributed Bragg reflector to form two types of blue RCLEDs. The electroluminescence spectra of the two RCLEDs show a much narrower linewidth, reduced from 32 nm in the conventional LED to ~5 nm, together with stable peak wavelength with increasing current density, with the shift reduced from 9.3 nm to less than 1 nm. The far-field pattern is influenced by the bottom mirror, and the far-field divergence angle can be decreased to only 52° by matching the cavity and the quantum well exciton modes. This scalable approach is highly promising for the realization of compact resonant cavity devices and their use in displays and in communications.

physics.optics↗

arXiv2025

An Empirical Study for Representations of Videos in Video Question Answering via MLLMs

Multimodal large language models have recently achieved remarkable progress in video question answering (VideoQA) by jointly processing visual, textual, and audio information. However, it remains unclear which video representations are most effective for MLLMs, and how different modalities balance task accuracy against computational efficiency. In this work, we present a comprehensive empirical study of video representation methods for VideoQA with MLLMs. We systematically evaluate single modality inputs question only, subtitles, visual frames, and audio signals as well as multimodal combinations, on two widely used benchmarks: VideoMME and LongVideoBench. Our results show that visual frames substantially enhance accuracy but impose heavy costs in GPU memory and inference latency, while subtitles provide a lightweight yet effective alternative, particularly for long videos. These findings highlight clear trade-offs between effectiveness and efficiency and provide practical insights for designing resource-aware MLLM-based VideoQA systems.

cs.IR↗

arXiv2025

Multifractal-enriched mobility edges and emergent quantum phases in Rydberg atomic arrays

Anderson localization describes disorder-induced phase transitions, distinguishing between localized and extended states. In quasiperiodic systems, a third multifractal state emerges, characterized by unique energy and wave functions. However, the corresponding multifractal-enriched mobility edges and three-state-coexisting quantum phases have yet to be experimentally detected. In this work, we propose exactly-solvable one-dimensional quasiperiodic lattice models that simultaneously host three-state-coexisting quantum phases, with their phase boundaries analytically derived via Avila's global theorem. Furthermore, we propose experimental protocols via Rydberg atom arrays to realize these states. Notably, we demonstrate a spectroscopic technique capable of measuring inverse participation ratios across real-space and dual-space domains, enabling simultaneous characterization of localized, extended, and multifractal quantum phases in systems with up to tens of qubits. Our work opens new avenues for the experimental exploration of Anderson localization and multifractal states in artificial quantum systems.

cond-mat.dis-nn↗

arXiv2025

Lovász Meets Lieb-Schultz-Mattis: Complexity in Approximate Quantum Error Correction

Approximate quantum error correction (AQEC) provides a versatile framework for both quantum information processing and probing many-body entanglement. We reveal a fundamental tension between the error-correcting power of an AQEC and the hardness of code state preparation. More precisely, through a novel application of the Lovász local lemma, we establish a fundamental trade-off between local indistinguishability and circuit complexity, showing that orthogonal short-range entangled states must be distinguishable via a local operator. These results offer a powerful tool for exploring quantum circuit complexity across diverse settings. As applications, we derive stronger constraints on the complexity of AQEC codes with transversal logical gates and establish strong complexity lower bounds for W state preparation. Our framework also provides a novel perspective for systems with Lieb-Schultz-Mattis type constraints.

quant-ph↗

arXiv2025

GlobalTomo: A global dataset for physics-ML seismic wavefield modeling and FWI

Global seismic tomography, taking advantage of seismic waves from natural earthquakes, provides essential insights into the earth's internal dynamics. Advanced Full-waveform Inversion (FWI) techniques, whose aim is to meticulously interpret every detail in seismograms, confront formidable computational demands in forward modeling and adjoint simulations on a global scale. Recent advancements in Machine Learning (ML) offer a transformative potential for accelerating the computational efficiency of FWI and extending its applicability to larger scales. This work presents the first 3D global synthetic dataset tailored for seismic wavefield modeling and full-waveform tomography, referred to as the GlobalTomo dataset. This dataset is uniquely comprehensive, incorporating explicit wave physics and robust geophysical parameterization at realistic global scales, generated through state-of-the-art forward simulations optimized for 3D global wavefield calculations. Through extensive analysis and the establishment of ML baselines, we illustrate that ML approaches are particularly suitable for global FWI, overcoming its limitations with rapid forward modeling and flexible inversion strategies. This work represents a cross-disciplinary effort to enhance our understanding of the earth's interior through physics-ML modeling.

physics.geo-ph↗

arXiv2025

High-throughput computational framework for lattice dynamics and thermal transport including high-order anharmonicity: an application to cubic and tetragonal inorganic compounds

Accurately predicting lattice thermal conductivity (kL) from first principles remains a challenge in identifying materials with extreme thermal behavior. While modern lattice dynamics methods enable routine predictions of kL within the harmonic approximation and three-phonon scattering framework (HA+3ph), reliable results, especially for low-kL compounds, require higher-order anharmonic effects, including self-consistent phonon renormalization, four-phonon scattering, and off-diagonal heat flux (SCPH+3,4ph+OD). We present a high-throughput workflow integrating these effects into a unified framework. Using this, we compute kL for 773 cubic and tetragonal inorganic compounds across diverse chemistries and structures. From 562 dynamically stable compounds, we assess the hierarchical effects of higher-order anharmonicity. For about 60% of materials, HA+3ph predictions closely match those from SCPH+3,4ph+OD. However, SCPH corrections often increase kL, sometimes by over 8 times, while four-phonon scattering universally reduces it, occasionally to 15% of the HA+3ph value. Off-diagonal contributions are minor in high-kL systems but can be comparable to the diagonal ones in highly anharmonic, low-kL compounds. We highlight four cases-Rb2TlAlH6, Cu3VS4, CuBr, and KTlCl4-exhibiting distinct anharmonic behaviors. This work delivers not only a robust workflow for high-fidelity kL dataset but also a quantitative framework to determine when higher-order effects are essential. The hierarchy of kL results, from the HA+3ph to SCPH+3,4ph+OD level, offers a scalable, interpretable route to discovering next-generation extreme thermal materials.

cond-mat.mtrl-sci↗

arXiv2025

Emergent multi-loop nested point gap in a non-Hermitian quasiperiodic lattice

We propose a geometric series modulated non-Hermitian quasiperiodic lattice model, and explore its localization and topological properties. The results show that with the ever-increasing summation terms of the geometric series, multiple mobility edges and non-Hermitian point gaps with high winding number can be induced in the system. The point gap spectrum of the system has a multi-loop nested structure in the complex plane, resulting in a high winding number. In addition, we analyze the limit case of summation of infinite terms. The results show that the mobility edges merge together as only one mobility edge when summation terms are pushed to the limit. Meanwhile, the corresponding point gaps are merged into a ring with winding number equal to one. Through Avila's global theory, we give an analytical expression for mobility edges in the limit of infinite summation, reconfirming that mobility edges and point gaps do merge and will result in a winding number that is indeed equal to one.

cond-mat.dis-nn↗

arXiv2025

GSTM-HMU: Generative Spatio-Temporal Modeling for Human Mobility Understanding

Human mobility traces, often recorded as sequences of check-ins, provide a unique window into both short-term visiting patterns and persistent lifestyle regularities. In this work we introduce GSTM-HMU, a generative spatio-temporal framework designed to advance mobility analysis by explicitly modeling the semantic and temporal complexity of human movement. The framework consists of four key innovations. First, a Spatio-Temporal Concept Encoder (STCE) integrates geographic location, POI category semantics, and periodic temporal rhythms into unified vector representations. Second, a Cognitive Trajectory Memory (CTM) adaptively filters historical visits, emphasizing recent and behaviorally salient events in order to capture user intent more effectively. Third, a Lifestyle Concept Bank (LCB) contributes structured human preference cues, such as activity types and lifestyle patterns, to enhance interpretability and personalization. Finally, task-oriented generative heads transform the learned representations into predictions for multiple downstream tasks. We conduct extensive experiments on four widely used real-world datasets, including Gowalla, WeePlace, Brightkite, and FourSquare, and evaluate performance on three benchmark tasks: next-location prediction, trajectory-user identification, and time estimation. The results demonstrate consistent and substantial improvements over strong baselines, confirming the effectiveness of GSTM-HMU in extracting semantic regularities from complex mobility data. Beyond raw performance gains, our findings also suggest that generative modeling provides a promising foundation for building more robust, interpretable, and generalizable systems for human mobility intelligence.

cs.LG↗

arXiv2025

Towards personalized, precise and survey-free environment recognition: AI-enhanced sensor fusion without pre-deployment

Accurate and personalized environment recognition is essential for seamless indoor positioning and optimized connectivity, yet traditional fingerprinting requires costly site surveys and lacks user-level adaptation. We present a survey-free, on-device sensor-fusion framework that builds a personalized, lightweight multi-source fingerprint (FP) database from pedestrian dead reckoning (PDR), WiFi/cellular, GNSS, and interaction time tags. Matching is performed by an AI-enhanced dynamic time warping module (AIDTW) that aligns noisy, asynchronous sequences. To turn perception into continually improving actions, a cloud-edge online Reinforcement Learning from Human Feedback (RLHF) loop aggregates desensitized summaries and human feedback in the cloud to optimize a policy via proximal policy optimization (PPO), and periodically distills updates to devices. Across indoor/outdoor scenarios, our system reduces network-transition latency (measured by time-to-switch, TTS) by 32-65% in daily environments compared with conventional baselines, without site-specific pre-deployment.

eess.SP↗

arXiv2025

Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation

Computer-generated holography (CGH) has gained wide attention with deep learning-based algorithms. However, due to its nonlinear and ill-posed nature, challenges remain in achieving accurate and stable reconstruction. Specifically, ($i$) the widely used end-to-end networks treat the reconstruction model as a black box, ignoring underlying physical relationships, which reduces interpretability and flexibility. ($ii$) CNN-based CGH algorithms have limited receptive fields, hindering their ability to capture long-range dependencies and global context. ($iii$) Angular spectrum method (ASM)-based models are constrained to finite near-fields.In this paper, we propose a Deep Unfolding Network (DUN) that decomposes gradient descent into two modules: an adaptive bandwidth-preserving model (ABPM) and a phase-domain complex-valued denoiser (PCD), providing more flexibility. ABPM allows for wider working distances compared to ASM-based methods. At the same time, PCD leverages its complex-valued deformable self-attention module to capture global features and enhance performance, achieving a PSNR over 35 dB. Experiments on simulated and real data show state-of-the-art results.

cs.CV↗